Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    How to, tips, lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    complexity
    0.40
     habitation
    0.39
     omission
    0.39
     Ausgang
    0.38
    ⊆
    0.38
     voorzien
    0.37
     generality
    0.37
     existencia
    0.37
     ಅಪ
    0.37
     상당히
    0.37
    POSITIVE LOGITS
    How
    1.09
     Cómo
    1.09
    Tips
    1.08
     How
    1.06
     Tips
    1.05
    Cómo
    1.05
     tips
    0.98
    如何
    0.98
     如何
    0.97
    如何在
    0.95
    Act Density 0.011%

    No Known Activations